一、spark-submit腳本內容分析
if [ -z "${SPARK_HOME}" ]; then
source "$(dirname "$0")"/find-spark-home
fi
# disable randomized hash for string in Python 3.3+
export PYTHONHASHSEED=0
exec "${SPARK_HOME}"/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"
- 首先會檢查是否設置了SPARK_HOME,
- 如果沒有則會執行find-spark-home腳本,來自動設置SPARK_HOME到環境變量;
- 如果SPARK_HOME已經存在,就會執行spark-class腳本,spark-classs腳本檢查一序列的環境變量、spark jars 以及用戶設置的參數是否正確等,最後會執行org.apache.spark.deploy.SparkSubmit類。
二、SparkSubmit
首先找到main方法
override def main(args: Array[String]): Unit = {
val submit = new SparkSubmit() {
self =>
override protected def parseArguments(args: Array[String]): SparkSubmitArguments = {
new SparkSubmitArguments(args) {
override protected def logInfo(msg: => String): Unit = self.logInfo(msg)
override protected def logWarning(msg: => String): Unit = self.logWarning(msg)
}
}
override protected def logInfo(msg: => String): Unit = printMessage(msg)
override protected def logWarning(msg: => String): Unit = printMessage(s"Warning: $msg")
override def doSubmit(args: Array[String]): Unit = {
try {
super.doSubmit(args)
} catch {
case e: SparkUserAppException =>
exitFn(e.exitCode)
}
}
}
submit.doSubmit(args)
}
最後調用了doSubmit()方法
def doSubmit(args: Array[String]): Unit = {
// Initialize logging if it hasn't been done yet. Keep track of whether logging needs to
// be reset before the application starts.
val uninitLog = initializeLogIfNecessary(true, silent = true)
val appArgs = parseArguments(args)
if (appArgs.verbose) {
logInfo(appArgs.toString)
}
appArgs.action match {
case SparkSubmitAction.SUBMIT => submit(appArgs, uninitLog)
case SparkSubmitAction.KILL => kill(appArgs)
case SparkSubmitAction.REQUEST_STATUS => requestStatus(appArgs)
case SparkSubmitAction.PRINT_VERSION => printVersion()
}
}
其中parseArguments
用來解析參數,然後根據參數解析的結果跳轉到相應的操作;這裏跳轉到SUBMIT。
此時調用了submit()這個方法
private def submit(args: SparkSubmitArguments, uninitLog: Boolean): Unit = {
def doRunMain(): Unit = {
if (args.proxyUser != null) {
val proxyUser = UserGroupInformation.createProxyUser(args.proxyUser,
UserGroupInformation.getCurrentUser())
try {
proxyUser.doAs(new PrivilegedExceptionAction[Unit]() {
override def run(): Unit = {
runMain(args, uninitLog)
}
})
} catch {
case e: Exception =>
// Hadoop's AuthorizationException suppresses the exception's stack trace, which
// makes the message printed to the output by the JVM not very helpful. Instead,
// detect exceptions with empty stack traces here, and treat them differently.
if (e.getStackTrace().length == 0) {
error(s"ERROR: ${e.getClass().getName()}: ${e.getMessage()}")
} else {
throw e
}
}
} else {
runMain(args, uninitLog)
}
}
// In standalone cluster mode, there are two submission gateways:
// (1) The traditional RPC gateway using o.a.s.deploy.Client as a wrapper
// (2) The new REST-based gateway introduced in Spark 1.3
// The latter is the default behavior as of Spark 1.3, but Spark submit will fail over
// to use the legacy gateway if the master endpoint turns out to be not a REST server.
if (args.isStandaloneCluster && args.useRest) {
try {
logInfo("Running Spark using the REST application submission protocol.")
doRunMain()
} catch {
// Fail over to use the legacy submission gateway
case e: SubmitRestConnectionException =>
logWarning(s"Master endpoint ${args.master} was not a REST server. " +
"Falling back to legacy submission gateway instead.")
args.useRest = false
submit(args, false)
}
// In all other modes, just run the main class as prepared
} else {
doRunMain()
}
}
首先會判斷cluster mode,這裏不考慮standalone模式,所以會直接來到 doRunMain() 方法。在 doRunMain() 中,首先會檢查用戶權限,然後會調用runMain(args, uninitLog)這個核心方法,
private def runMain(args: SparkSubmitArguments, uninitLog: Boolean): Unit = {
val (childArgs, childClasspath, sparkConf, childMainClass) = prepareSubmitEnvironment(args)
// Let the main class re-initialize the logging system once it starts.
if (uninitLog) {
Logging.uninitialize()
}
if (args.verbose) {
logInfo(s"Main class:\n$childMainClass")
logInfo(s"Arguments:\n${childArgs.mkString("\n")}")
// sysProps may contain sensitive information, so redact before printing
logInfo(s"Spark config:\n${Utils.redact(sparkConf.getAll.toMap).mkString("\n")}")
logInfo(s"Classpath elements:\n${childClasspath.mkString("\n")}")
logInfo("\n")
}
val loader =
if (sparkConf.get(DRIVER_USER_CLASS_PATH_FIRST)) {
new ChildFirstURLClassLoader(new Array[URL](0),
Thread.currentThread.getContextClassLoader)
} else {
new MutableURLClassLoader(new Array[URL](0),
Thread.currentThread.getContextClassLoader)
}
Thread.currentThread.setContextClassLoader(loader)
for (jar <- childClasspath) {
addJarToClasspath(jar, loader)
}
var mainClass: Class[_] = null
try {
mainClass = Utils.classForName(childMainClass)
} catch {
case e: ClassNotFoundException =>
logWarning(s"Failed to load $childMainClass.", e)
if (childMainClass.contains("thriftserver")) {
logInfo(s"Failed to load main class $childMainClass.")
logInfo("You need to build Spark with -Phive and -Phive-thriftserver.")
}
throw new SparkUserAppException(CLASS_NOT_FOUND_EXIT_STATUS)
case e: NoClassDefFoundError =>
logWarning(s"Failed to load $childMainClass: ${e.getMessage()}")
if (e.getMessage.contains("org/apache/hadoop/hive")) {
logInfo(s"Failed to load hive class.")
logInfo("You need to build Spark with -Phive and -Phive-thriftserver.")
}
throw new SparkUserAppException(CLASS_NOT_FOUND_EXIT_STATUS)
}
val app: SparkApplication = if (classOf[SparkApplication].isAssignableFrom(mainClass)) {
mainClass.newInstance().asInstanceOf[SparkApplication]
} else {
// SPARK-4170
if (classOf[scala.App].isAssignableFrom(mainClass)) {
logWarning("Subclasses of scala.App may not work correctly. Use a main() method instead.")
}
new JavaMainApplication(mainClass)
}
@tailrec
def findCause(t: Throwable): Throwable = t match {
case e: UndeclaredThrowableException =>
if (e.getCause() != null) findCause(e.getCause()) else e
case e: InvocationTargetException =>
if (e.getCause() != null) findCause(e.getCause()) else e
case e: Throwable =>
e
}
try {
app.start(childArgs.toArray, sparkConf)
} catch {
case t: Throwable =>
throw findCause(t)
}
}
在這個方法中,首先會設置classpath, system properties, and application arguments來準備啓動環境;然後會通過反射的方式獲取到我們提交的主類,最後會通過app.start方法,拿到main方法,
override def start(args: Array[String], conf: SparkConf): Unit = {
val mainMethod = klass.getMethod("main", new Array[String](0).getClass)
if (!Modifier.isStatic(mainMethod.getModifiers)) {
throw new IllegalStateException("The main method in the given main class must be static")
}
val sysProps = conf.getAll.toMap
sysProps.foreach { case (k, v) =>
sys.props(k) = v
}
mainMethod.invoke(null, args)
}
最後通過mainMethod.invoke(null, args)
啓動任務。